# US 2020/0401629 A1 · Suggesting queries based upon keywords > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401629 A1 - Document ID: US20200401629A1 - Status: Published application - Kind: A1 - Application number: 16/448,132 - Filed: 2019-06-21 - Published: 2020-12-24 - Earliest claimed: 2019-06-21 - Assignees: Oath Inc. - Applicants: Oath Inc. - Inventors: Su-Chen Lin; Jian-Chih Ou; Tzu-Chiang Liou; Wei-Lun Su - Web page: https://patentgrep.com/patent/US20200401629A1 ## CPC - G06F 16/2428: {Query predicate definition using graphical user interfaces, including menus and forms (G06F16/2423 takes precedence)} - G06F 16/24578: {using ranking} - G06F 16/90324: {using system suggestions} - G06F 16/951: Indexing; Web crawling techniques - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates. ## Claims ### Claim 1 A method, comprising: controlling a graphical user interface of a first device to display a search interface; receiving one or more keywords, via the search interface, from the first device; determining, based upon the one or more keywords and a historical query database comprising a plurality of historical queries, a plurality of queries associated with the one or more keywords; generating, based upon a plurality of search sessions associated with the plurality of historical queries, a plurality of relationship scores associated with the plurality of queries, wherein: a first search session of the plurality of search sessions corresponds to one or more searches performed via a second device using one or more queries of the plurality of historical queries; and a relationship score of the plurality of relationship scores is associated with a relationship between a query of the plurality of queries and the one or more keywords; analyzing the historical query database to determine a plurality of click rates associated with the plurality of queries; and generating, based upon the plurality of queries, the plurality of relationship scores and the plurality of click rates, a list of suggested queries associated with the one or more keywords. ### Claim 2 (depends on 1) The method of claim 1, comprising: ranking the plurality of queries based upon the plurality of relationship scores and the plurality of click rates to generate a plurality of rankings associated with the plurality of queries, wherein the generating the list of suggested queries is performed based upon the plurality of rankings. ### Claim 3 (depends on 2) The method of claim 2, wherein the list of suggested queries comprises a first suggested query above a second suggested query based upon a first ranking of the first suggested query being higher than a second ranking of the second suggested query. ### Claim 4 (depends on 1) The method of claim 1, comprising: presenting, via the search interface, one or more suggested queries of the list of suggested queries. ### Claim 5 (depends on 2) The method of claim 2, comprising: determining that one or more rankings associated with one or more suggested queries of the list of suggested queries meet a rank threshold; and presenting, via the search interface, the one or more suggested queries. ### Claim 6 (depends on 1) The method of claim 1, comprising: receiving a first query, of the one or more queries associated with the first search session, from the second device during the first search session at a first time; receiving a second query, of the one or more queries associated with the first search session, from the second device during the first search session at a second time after the first time; and determining a sequence of queries associated with the first search session based upon the first query and the second query, wherein: the sequence of queries is indicative of the second query being received after the first query is received; the generating the plurality of relationship scores is performed based upon a plurality of sequences of queries associated with the plurality of search sessions; and the plurality of sequences of queries comprises the sequence of queries. ### Claim 7 (depends on 1) The method of claim 1, comprising: determining a first query path associated with the one or more keywords, wherein the first query path comprises a first query, of the plurality of queries, corresponding to a first step of the first query path and one or more second queries, of the plurality of queries, corresponding to a second step of the first query path; and determining a second query path associated with the one or more keywords, wherein the second query path comprises a third query, of the plurality of queries, corresponding to a first step of the second query path and one or more fourth queries, of the plurality of queries, corresponding to a second step of the second query path. ### Claim 8 (depends on 7) The method of claim 7, wherein the generating the list of suggested queries comprises including the first query corresponding to the first step of the first query path and the third query corresponding to the first step of the second query path in the list of suggested queries. ### Claim 9 (depends on 8) The method of claim 8, comprising: presenting at least a portion of the list of suggested queries comprising the first query corresponding to the first step of the first query path and the third query corresponding to the first step of the second query path; receiving a selection of the first query corresponding to the first step of the first query path; and presenting, based upon the selection of the first query corresponding to the first step of the first query path, the one or more second queries corresponding to the second step of the first query path. ### Claim 10 (depends on 1) The method of claim 1, comprising: removing queries from the plurality of queries responsive to determining that the queries are associated with relationship scores that do not meet a threshold relationship score. ### Claim 11 (depends on 1) The method of claim 1, wherein the one or more keywords correspond to a query, the method comprising: presenting, via the search interface, a plurality of search results corresponding to a plurality of web pages associated with the one or more keywords. ### Claim 12 (depends on 1) The method of claim 1, wherein the one or more keywords correspond to a query, the method comprising: generating a first set of search results based upon the one or more keywords; generating a second set of search results based upon the list of suggested queries; and presenting, via the search interface, a plurality of search results corresponding to a plurality of web pages, wherein the plurality of search results comprises the first set of search results associated with the one or more keywords and the second set of search results associated with the list of suggested queries. ### Claim 13 (depends on 2) The method of claim 2, wherein the one or more keywords correspond to a query, the method comprising: generating a plurality of search results corresponding to a plurality of web pages associated with the one or more keywords; ranking the plurality of search results based upon at least one of the plurality of rankings or the list of suggested queries to generate a second plurality of rankings associated with the plurality of search results; generating a ranked list of search results based upon the plurality of search results and the second plurality of rankings; and presenting, via the search interface, the ranked list of search results. ### Claim 14 (depends on 1) The method of claim 1, wherein a search session of the plurality of search sessions is associated with a sequence of queries, the method comprising: training a machine learning model using a plurality of sequences of queries associated with the plurality of search sessions, wherein the plurality of sequences of queries are associated with the one or more keywords. ### Claim 15 (depends on 14) The method of claim 14, wherein the plurality of relationship scores is generated using the machine learning model. ### Claim 16 (depends on 14) The method of claim 14, wherein the list of suggested queries is generated using the machine learning model. ### Claim 17 A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising: controlling a graphical user interface of a first device to display a search interface; receiving one or more keywords, via the search interface, from the first device; determining, based upon the one or more keywords and a historical query database comprising a plurality of historical queries, a plurality of queries associated with the one or more keywords; generating, based upon a plurality of search sessions associated with the plurality of historical queries, a plurality of relationship scores associated with the plurality of queries, wherein: a first search session of the plurality of search sessions corresponds to one or more searches performed via a second device using one or more queries of the plurality of historical queries; and a relationship score of the plurality of relationship scores is associated with a relationship between a query of the plurality of queries and the one or more keywords; and generating, based upon the plurality of queries and the plurality of relationship scores, a list of suggested queries associated with the one or more keywords. ### Claim 18 (depends on 17) The non-transitory machine readable medium of claim 17, the operations comprising: ranking the plurality of queries based upon the plurality of relationship scores to generate a plurality of rankings associated with the plurality of queries, wherein the generating the list of suggested queries is performed based upon the plurality of rankings. ### Claim 19 A computing device comprising: a processor; and memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising: controlling a graphical user interface of a first device to display a search interface; receiving one or more keywords, via the search interface, from the first device; determining, based upon the one or more keywords and a historical query database comprising a plurality of historical queries, a plurality of queries associated with the one or more keywords; generating, based upon a plurality of search sessions associated with the plurality of historical queries, a plurality of relationship scores associated with the plurality of queries, wherein: a first search session of the plurality of search sessions corresponds to one or more searches performed via a second device using one or more queries of the plurality of historical queries; and a relationship score of the plurality of relationship scores is associated with a relationship between a query of the plurality of queries and the one or more keywords; analyzing the historical query database to determine a plurality of click rates associated with the plurality of queries; and generating, based upon the plurality of queries, the plurality of relationship scores and the plurality of click rates, a list of suggested queries associated with the one or more keywords. ### Claim 20 (depends on 19) The computing device of claim 19, the operations comprising: ranking the plurality of queries based upon the plurality of relationship scores and the plurality of click rates to generate a plurality of rankings associated with the plurality of queries, wherein the generating the list of suggested queries is performed based upon the plurality of rankings.